www.ijecs.in
International Journal Of Engineering And Computer Science ISSN:2319-7242
Volume 3 Issue 11 November, 2014 Page No. 9003-9106
Fingerprint Matching with Ridge Ends and Virtual Core Point
using Enhanced Concentric Ring Algorithim
Gurpreet Singh1, Vinod Kumar3
1
CSE Department,
Guru Kashi University,
Talwandi Sabo, Punjab, India
gurpreetgill72@gmail.com
2
AP, CSE Department,
Guru Kashi University,
Talwandi Sabo, Punjab, India
vinod_sharma85@rediffmail.com
Abstract: Fingerprints are the most common and widely accepted biometric feature for person identification and verification in the field of
biometric identification. Fingerprints consists of two main types of features : (i) Ridge and Furrow structure: R idge ends and
bifurcation and (ii) Core Point: the of maximum curvature in central region of the fingerprint. This paper presents the implementation of
a minutiae based approach to fingerprint identification and verification and serves as a review of the different techniqu es used in various
steps in the development of minutiae based Automatic Fingerprint Identification System (AFIS). The technique conferred in this
paper is based on the extraction of ridge termination and virtual core minutiae from the thinned, binarized and segmented version of a
fingerprint image.
Keywords: Fingerprint, Core, Ridge End, Minutiae Extraction, Minutiae Matching
operations.
1. Introduction
With the recent development in information technology,
the need for secure personal authentication systems has
increased rapidly. Earlier, IC cards and passwords are widely
used and are popular in personal authentication. However,
these methods have several drawbacks. The IC cards could be
stolen or duplicated, and in the case of passwords, they could
become known to others, this makes it insecure.
Fingerprints have been used for biometric recognition
since long because of their high accuracy, immutability and
individuality[2]. Immutability is defined as the persistence of
the fingerprints over time whereas individuality is the
uniqueness of ridge details across individuals. Fingerprint
authentication is one of the most important biometric
technologies [4]. A fingerprint is the pattern of ridges and
valleys (furrows) on the surface of the finger. This paper
focuses on fingerprints, which can provide personal
authentication at high accuracy. Firstly, Fingerprint image is
obtained from sensor. And this image is enhanced because
enhancement algorithm can improve the clarity of the ridge
structures
of input fingerprint images, then the
enhancement image is binarized by fixing the threshold
value. The binarization image is thinned using morphological
Then the output image is segmented for minutiae extraction.
After minutiae extraction, false minutiae are removed by using
Euclidean distance. After pre-processing, the existing data
collection and template data collection are matched by using
two steps (registration and verification).
Figure. Fingerprint Pattern
For the fingerprint image pre-processing stage, Histogram
Equalization and Fourier Transform is used to do image
enhancement [8] [29]. And then the fingerprint image is
binarized using the locally adaptive threshold method [5] [12].
The image segmentation task is fulfilled by a three-step
approach: block direction estimation, segmentation by direction
intensity [4] and Region of Interest extraction by
Gurpreet Singh1 IJECS Volume 3. Issue 11 November, 2014 Page No.9103-9106
Page 9103
Morphological operations. Also the morphological operations
for extraction ROI are used for fingerprint image segmentation.
For minutia extraction stage, three thinning algorithms [12]
[2] are tested and the Morphological thinning operation is
finally bid out with high efficiency and pretty good thinning
quality. My technique for minutia extraction is carried out in
two phases, in first phase, virtual core point is calculated which
is the main and initial identification feature.
Once the virtual core in the centermost region of the
fingerprint image(in case of no core point) is identified, its x-y
coordinates and angle of rotation is stored in database (Table
1) as primary identifying feature and in second phase, rest of
the minutia are extracted and stored as secondary identifying
feature in another database (Table 2). Most methods used in
the minutia extraction stage are developed by other researchers
but they form a brand new combination in my paper. The
minutia marking is a simple task as most literatures reported but
one special case is found during my implementation and an
additional check mechanism is enforced to avoid such kind of
oversight.
For the post processing stage, an existing algorithm is used
to remove false minutia based on [12][1]. The superficial
approach of minutia matching mechanism is one of the main
proposed modifications in this paper to achieve efficient
results. When minutia matcher initiates, it search and identifies
the Virtual Core Point / Reference Point only from the
fingerprints from the fingerprint scanning device and compares
them among the values stored in fingerprint database. Once the
Virtual Core Point is identified, the matcher compares the interdistance between the core and the nearest bifurcation to ensure
the identified result. If the inter-distance between the
core/reference minutia and nearest bifurcation minutia match
well [1], two fingerprint images are aligned and matching is
conducted for all remaining minutia.
Implementing the comparison of only Virtual Core Point first
results in quick matching among millions of fingerprints in
database. Moreover, confirmation of inter-distance between the
core and the nearest bifurcation ensures avoiding any kind of
oversight. Implementation of this technique uses lesser CPU
time and makes system lightweight, quick and more efficient
thereby reducing the total overhead..
2. Proposed Technique
Matching is accomplished in two phases: Initial Matching and
Final Matching
2.1 Initial Matching
1. Coordinates of Virtual core point (VCP) i.e. (x, y) are identified
and values are stored in Primary Table 1.
2. The coordinates of nearest ridge end to the VCP are found
using Enhanced Concentric Ring algorithm are found and
stored in Primary Table 1.
3. Coordinate values of VCP and Ridge End along with Interdistance(r) is used as the Primary matching feature at
identification level in Primary Table 1.
2.2 Enhanced Concentric Ring Algorithm
1. Identify the coordinates of all the minutiae present in
fingerprint and store in Secondary Table 2.
2. Find types of all the minutiae in Secondary Table 2.
3. If MINUTIA TYPE = Ridge End, then transfer x and y
coordinate values to Secondary Table 1 else skip the values.
4. Identify the coordinate values of VCP (x, y) using [28].
5. Use VCP(x, y) as the center and radius(r) = 1 (in pixels)
6. Draw imaginary circle and compare each pixel on
circumference of circle with values in Secondary table 1,
starting from direction of VCP in clockwise manner.
7. If minutia matches then inter-distance radius = r and exit, else
search for next minutia with same radius.
8. If no minutia match using same radius, then radius = radius+1
and go to step 6.Set your page as A4, width 210, height 297 and
margins as follows:
Table 1: Primary Table 1
Virtual Core Point
Nearest Ridge
coordinates
End coordinates
X Axis
Y Axis
Angle
X Axis
Y Axis
62
104
0.64
51
105
InterDistance
r
(in pixel)
9
2.3 Final Matching
When initial matching is done, rest of the minutiae in fingerprint
which are stored in Secondary Table 2 are matched to confirm
the result.
Table 1: Secondary Table 2
X Axis
Y Axis
Angle 1
Angle 2
Angle 3
52
26
0.00
0
0
58
29
3.14
0
0
42
43
-2.62
0
0
154
58
2.36
0
0
52
59
0.52
0
0
180
79
-1.05
0
0
61
92
-2.09
0
0
93
98
-1.57
0
0
137
116
-1.57
0
0
151
116
-1.05
0
0
108
117
-2.09
0
0
70
124
-0.79
0
0
162
126
-1.57
0
0
79
133
2.36
0
0
Gurpreet Singh1 IJECS Volume 3. Issue 11 November, 2014 Page No.9103-9106
Page 9104
146
13
2.36
NaN
-0.52
52
105
-2.36
1.57
-0.79
126
115
-2.36
1.57
-1.05
169
136
-2.36
2.09
-0.79
NaN
NaN
0.00
0.00
0.00
79
145
-1.05
-1.05
0.52
178
149
1.57
1.57
-0.79
77
153
2.09
2.09
0.00
Nan
NaN
0.00
0.00
0.00
90
167
2.36
-2.36
0.52
119
174
2.36
-2.09
0.00
the accuracy of these techniques is far from satisfactory. A new
mechanism is proposed that incorporates Gabor filtering &
Wavelet transformation.
References
The matching algorithm for the aligned minutia patterns needs
to be elastic since the strict match requiring that all parameters
(x, y, ) are the same for two identical core/reference minutia is
impossible due to the slight deformations and inexact
quantization of minutia.
The approach to match rest of minutia in secondary phase is
achieved by placing a close circuit box around each template
minutia. If the minutia to be matched is within the rectangle box
and the direction discrepancy between them is very small, then
the two minutiae are regarded as a matched minutia pair. Each
minutia in the template image either has no matched minutia or
has only one corresponding minutia.
The final match ratio for two fingerprints is the number of total
matched pair over the number of minutia of the template
fingerprint. The score is 100*ratio and ranges from 0 to 100. If
the score is larger than a pre-specified threshold, the two
fingerprints are from the same finger. However, the elastic
match algorithm has large computation complexity and is
vulnerable to spurious minutia.
3. Conclusions
At present the methods that are in use are the ones
involving the use of Gabor filtering and Fourier filtering.
The first technique consists of implementation of 2D
Fourier Transform for the enhancement stage. This is the
computationally fastest method since it classifies the
orientations to 16 directions. But this results in lesser accuracy
since it assumes the frequency to be constant throughout
which is not the case.
In the second method the improvement is done by introduction
of Gabor filters which takes into account both the frequency
and orientation of the image and the filtering is done with a
greater accuracy.
The Wavelet Transform has been found to be a very
effective tool in denoising and compression techniques. But
[1] Lin Hong. "Automatic Personal Identification Using
Fingerprints", Ph.D. Thesis, 1998.
[2] D.Maio and D. Maltoni. Direct gray-scale minutiae
detection in fingerprints. IEEE Trans. Pattern Anal. And
Machine Intell., 19(1):27-40, 1997.
[3] Jain, A.K., Hong, L., and Bolle, R., “On-Line Fingerprint
Verification,” IEEE Trans. On Pattern Anal and Machine
Intell, 19(4), pp. 302-314, 1997.
[4] N. Ratha, S. Chen and A.K. Jain, "Adaptive Flow
Orientation Based Feature Extraction in Fingerprint
Images", Pattern Recognition, Vol. 28, pp. 1657-1672,
November 1995.
[5] Alessandro Farina, Zsolt M.Kovacs -Vajna, Alberto leone,
Fingerprint minutiae extraction from skeletonized binary
images, Pattern Recognition, Vol.32, No.4, pp877-889,
1999.
[6] Lee, C.J., and Wang, S.D.: Fingerprint feature extration
using Gabor filters, Electron. Lett., 35, (4), pp.288-290,
1999.
[7] M. Tico, P.Kuosmanen and J.Saarinen. Wavelet domain
features for fingerprint recognition, Electroni. Lett., 37,
(1), pp.21-22, 2001.
[8] L. Hong, Y. Wan and A.K. Jain, "Fingerprint Image
Enhancement: Algorithms and Performance Evaluation",
IEEE Transactions on PAMI, Vol. 20, No. 8, pp.777-789,
August 1998.
[9] Manvjeet kaur, Mukhwinder singh, Akshay Girdhar and
Parvinder s. sandhu, “Fingerprint Verification System
using minutia extraction technique”, W orld Academy of
Sciences, Engineering and Technology 46, 2005.
[10] Jyoti Rajharia, P.C. Gupta, “A new and Effective Approach
for fingerprint Recognition by using feed forward back
propagation neural network”, International Journal of
Computer Applications (0975-8887), Volume 52- No.10,
August 2012.
[11] Romany F. Mansour, Abdul Samad A. Marghilani, “A new
technique to fingerprint recognition based on partial
window”, Computer Engineering and Intelligent Systems.
ISSN 2222-1719(Paper) ISSN 2222-2863 (Online) Vol.3,
No. 10, 2012.
[12] L.C. Jain, U. Halici, I. Hayashi, S.B. Lee and S. Tsutsui,
“Intelligent biometric techniques in fingerprint and face
recognition”, the CRC Press, 1999.
[13] M. J. Donahue and S. I. Rokhlin, "On the Use of Level
Curves in Image Analysis," Image Understanding, VOL.
57, pp 652 - 655, 1992.
[14] S.W. Lee B. H. Nam, “Fingerprint Recoginition Using
Wavelet Transform and Probabilistic Neural Network”
International Joint Conference on Neural Network, Vol.5,
pp.3276-3279, 1999.
[15] A.K. Jain, S. Prabhakar and L. Hong.”A Multichanel
Approach
to
FingerPrint Classification,” IEEE
Transactions on PAMI, Vol.21, No.4, pp.348-359, Apr.
1999
[16] Le Hoang Thai and Ha Nhat Tan, “Fingerprint recoginition
using standardized fingerprint model” IJCSI, Vol. 7, Issue
3, No.7, May 2010.
Gurpreet Singh1 IJECS Volume 3. Issue 11 November, 2014 Page No.9103-9106
Page 9105
[17] A. Mishra and M. Shandilya, “Fingerprint core point
detection using gradient field mask,” International
Journal of Computer Applications, vol. 2, no. 8, June
2010.
[18] A. Julasayvake and S. Choomchuay, “An Algorithm For
Fingerprint Core Point Detection,” International
Symposium on Signal Processing and Its Applications,
pp. 1-4, Feb. 2007.
[19] M. U. Munir and M. Y. Javed, “Fingerprint Matching
using Gabor Filters,” National Conference on Emerging
Technologies, Pakistan, pp. 147-152, 2004.
[20] C. T. Hsieh1, S.R. Shyu1 and K.M. Hung, „An Effective
Method for Fingerprint Classification” Tamkang Journal
of Science and Engineering, vol. 12, No. 2, pp. 169-182,
2009.
[21] Q. Zhao, D. Zhang, L. Zhang and N. Luo, “Adaptive
fingerprint pore modeling and extraction”, Pattern
Recognition, vol. 43, pp. 2833-2844, 2010.
[22] Vishal Shrivastava and Sumit Sharma, “Data Compression
of Fingerprint Minutiae”, International Journal of
Engineering Science and Technology (IJEST), Vol. 4, No.
2, Feburary 2012.
[23] A.K. Jain, S. Prabhakar, L. Hong and S. Pankanti,
“Filterbank-based fingerprint matching,”
IEEE
Transactions on Image Processing, vol. 9, no. 5, pp. 846859, 2000.
[24] Roopam Kumar Sharma, “Generation of Biometric Key for
use in DES”, International Journal of Computer Science
Isseues, Vol. 9, Issue 6, No.1, November 2012.
[25] Swapnali Mahadik, K.Narayanan, D.V. Bhoir and
Darshana Shah, “Access Control System using
fingerprint recoginition”, International Conference on
Advances in Computing, Communication and Control,
ICAC3 ’09, Page 306-311, 2009.
[26] Zin Mar Win and Myint Myint Sein, “An Effective
Fingerprint
Verification
System”,
International
Conference on Computer Science and Information
Technology (ICCSIT’2011) Pattaya Dec. 2011.
[27] Robert Newman, “Security and Access control using
Biometric Technologies”, Cengage Learning Inc. USA.
[28] Sarnali Basak, Md. Imdadul Islam, M.R. Amin, “Detection
of Virtual Core Point of A Fingerprint: A New
Approach”, International Journal of Soft Computing and
Engineering, Vol. 2, Issue-2, May 2012.
[29] Sangram Bana and Dr. Davinder Kaur, “Fingerprint
Recognition using Image Segmentation”, International
Journal of Advanced Engineering Sciences And
Technologies, Vol. 5, Issue no.1, 012-023, 2011.
Author Profile
Gurpreet S ingh is pursuing M .Tech. CSE from Guru Kashi
University, Talwandi Sabo. His area of interest are Digital Image
Procesing, mobile satellite communication systems, and wireless
networks.
Vinod Kumar is currently working as Assistant Professor in Dept. of
Computer Science and Engineering in Guru Kashi University,
Talwandi Sabo. His area of interest are Digital Image Processing,
Computer Networks, M ANET, and wireless networks.
Gurpreet Singh1 IJECS Volume 3. Issue 11 November, 2014 Page No.9103-9106
Page 9106